Alternativas para la medición partimos de una idea elemental: exportaciones por trabajador como proxy de la productividad ES posible que ahí las magnitudes jueguen un rol que rompa cosas por lo que mejor ponerlo en términos relativos

$\dfrac{X_{HS;s;p}}{L_{s,p}$

dos pistas que nos pueden ayudar a pensar:

$VCR = \dfrac{\dfrac{X_{HS;p}} {X_{HS;w}}} {\dfrac{X_p}{X_w}}$

Reescriendo también podría pensar en:

$LCR = \dfrac{\dfrac{L_{s;p}}{L_{s;w}}} {\dfrac{L_p}{L_w}}$

capital/trabajo intensivo:

$intensidad = \dfrac{\dfrac{VA_{s;p}}{VA_p}} {\dfrac{L_{s;p}}{L_p}}$

**opción 1**

$\dfrac{\dfrac{X_{HS;s;p}}{X_p}} {\dfrac{L_{s,p}}{L_p}}$

**opción 2**

$\dfrac{\dfrac{X_{HS;s;p}}{X_{HS;s;w}}} {\dfrac{L_{s,p}}{L_{s,w}}}$

opción 3
$\dfrac{VCR}{LCR}$

Preparación de bases

	t	country	k	v	expos_totales_pais	expos_mundo_producto	expos_totales_mundo	prop_expo	VCR	VCR_norm	VCR_existe	description
1	2002	af	80232	512.835	45183.569	302843.310	6.404218e+09	0.011350	240.018790	0.991702	1.0	Nuts, edible: walnuts, fresh or dried, shelled
2	2002	af	12111	819.028	45183.569	29169.439	6.404218e+09	0.018127	3979.754121	0.999498	1.0	Liquorice roots used primarily in perfumery, i...
3	2002	af	12119	80.016	45183.569	880996.538	6.404218e+09	0.001771	12.873250	0.855838	1.0	Plants and parts (including seeds and fruits) ...
4	2002	af	130212	1.155	45183.569	84206.964	6.404218e+09	0.000026	1.944104	0.320676	1.0	Vegetable saps and extracts: of liquorice
6	2002	af	540769	15.181	45183.569	848628.830	6.404218e+09	0.000336	2.535527	0.434313	1.0	Fabrics, woven: containing less than 85% by we...

Definiciones

	v	prop_hs_pais	prop_hs_mundo	prop_pais_mundo
v	1.000000	0.217609	0.430533	-0.007933
prop_hs_pais	0.217609	1.000000	0.075663	0.212244
prop_hs_mundo	0.430533	0.075663	1.000000	-0.016211
prop_pais_mundo	-0.007933	0.212244	-0.016211	1.000000

###############################    0       #########################
###############################    1       #########################
###############################    2       #########################
###############################    3       #########################
###############################    4       #########################
###############################    5       #########################
###############################    6       #########################
###############################    7       #########################
###############################    8       #########################
###############################    9       #########################

	runs	parametros	kl_score	best
0	0	{'perplexity': 15, 'metric': 'cosine'}	0.290841	TSNE(metric='cosine', n_iter=5000, perplexity=...
1	0	{'perplexity': 70, 'metric': 'correlation'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
2	0	{'perplexity': 70, 'metric': 'cosine'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
3	0	{'perplexity': 55, 'metric': 'cosine'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
4	0	{'perplexity': 60, 'metric': 'correlation'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
...	...	...	...	...
95	9	{'perplexity': 20, 'metric': 'cosine'}	0.254610	TSNE(metric='cosine', n_iter=5000, perplexity=...
96	9	{'perplexity': 20, 'metric': 'correlation'}	0.330467	TSNE(metric='cosine', n_iter=5000, perplexity=...
97	9	{'perplexity': 25, 'metric': 'correlation'}	0.315320	TSNE(metric='cosine', n_iter=5000, perplexity=...
98	9	{'perplexity': 60, 'metric': 'cosine'}	0.595184	TSNE(metric='cosine', n_iter=5000, perplexity=...
99	9	{'perplexity': 35, 'metric': 'cosine'}	0.431405	TSNE(metric='cosine', n_iter=5000, perplexity=...

100 rows × 4 columns

1

2

3

4

5

6

	runs	parametros	kl_score	best
0	0	{'perplexity': 15, 'metric': 'cosine'}	0.290841	TSNE(metric='cosine', n_iter=5000, perplexity=...
1	0	{'perplexity': 70, 'metric': 'correlation'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
2	0	{'perplexity': 70, 'metric': 'cosine'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
3	0	{'perplexity': 55, 'metric': 'cosine'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
4	0	{'perplexity': 60, 'metric': 'correlation'}	0.594407	TSNE(metric='cosine', n_iter=5000, perplexity=...
...	...	...	...	...
95	9	{'perplexity': 20, 'metric': 'cosine'}	0.254610	TSNE(metric='cosine', n_iter=5000, perplexity=...
96	9	{'perplexity': 20, 'metric': 'correlation'}	0.330467	TSNE(metric='cosine', n_iter=5000, perplexity=...
97	9	{'perplexity': 25, 'metric': 'correlation'}	0.315320	TSNE(metric='cosine', n_iter=5000, perplexity=...
98	9	{'perplexity': 60, 'metric': 'cosine'}	0.595184	TSNE(metric='cosine', n_iter=5000, perplexity=...
99	9	{'perplexity': 35, 'metric': 'cosine'}	0.431405	TSNE(metric='cosine', n_iter=5000, perplexity=...

100 rows × 4 columns

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[77], line 3
      1 new_sector1 = new_sector.merge(empleo[['country', 'time', 'cod_numeric', 'empleo' ]], left_on=['country', 't' , 'CIIU_2d'], right_on=['country', 'time', 'cod_numeric'], how= 'left')
      2 new_sector1['productividad'] = new_sector1.v/new_sector1.empleo
----> 3 plot_clusters_productivity(new_sector1, 'productividad')

TypeError: plot_clusters_productivity() missing 1 required positional argument: 'df_cluster'